Zero Zeng
Zero Zeng
> [07/28/2022-12:39:22] [I] [TRT] Searching for plugin: AliasWithName, plugin_version: 1, plugin_namespace: [07/28/2022-12:39:22] [E] [TRT] ModelImporter.cpp:773: While parsing node number 0 [AliasWithName -> "297"]: [07/28/2022-12:39:22] [E] [TRT] ModelImporter.cpp:774: --- Begin node...
If you enable the verbose log ``` class Logger : public ILogger { void log(Severity severity, const char* msg) noexcept override { std::cout >>>>>>>>>>>>> Chose Runner Type: DLA Tactic: 0x0000000000000003...
to solve this, you need to enable all allowed formats for DLA FP16 for the input and the output. refer to https://docs.nvidia.com/deeplearning/tensorrt/developer-guide/index.html#restrictions-with-dla modify your code with ``` ... input->setAllowedFormats(TensorFormats(1U
Getting “failed to import metagraph” when running the TRT saved_model converter workflow for TF 1.15
Looks like a TF bug or a tf2onnx bug?
can you share the model here?
@kevinch-nv We don't support negative pad value in parser? we parse the pad operator as ISliceLayer right?
#assertionD:\MMbushu\mmdeploy\csrc\mmdeploy\backend_ops\tensorrt\batched_nms\trt_batched_nms.cpp,103
Please describe your problem in more detail. I don't get what you mean. Also, looks like it's not a issue of TRT but `mmdeploy`. Perhaps it would be better to...
It should be released in a few days, most likely by the end of July.
May I ask what's the purpose of the two models with the same nodes but in different orders? I just think the order of computing surely will affect the final...